APK संस्करण
APK फ़ाइलें मूल रिपॉज़िटरी से मिलती हैं।
संस्करण में बदलाव
- Added support for reasoning models. VScan now allows configuring the amount of tokens a config can spend on a task, and setting the reasoning effort to be used in the process. - The conversation screen got a major rewamp. Now it offers detailed information about token usage of the entire conversation, as well as individual generated messages. If the model includes reasoning in its output, it can be displayed separately for each response. The conversation list now also supports accessibility ac
SHA-256 चेकसम
68d39988a200188624b0a770c4fec8ae8ba8e54e4ae44935447e928f9f1cf51eसंस्करण में बदलाव
- There is now a standalone editor for entering the system prompt and user prompt. This editor has a large text field, which should make it easy to work with long and complex prompts. - Various UI improvements and bug fixes.
SHA-256 चेकसम
0564dabbf3aae9df6a00cd0ca2e3517339f504b81998d84a1400c16379205354स्क्रीनशॉट
इस ऐप के बारे में
मूल विवरण अंग्रेज़ी में हैThis is a little project of mine aiming to research how vision LLMs could help out blind people on travel and in their every-day life by substituting eyesight for various visual tasks. VScan turns your smartphone's camera into a device for visual perception. You can define various optical cognitive functions, like looking for objects, signs, evaluating a scene or simply mediating visual impressions. You can afterwards use these functions on the camera view, just like a sighted person would use their eyes to achieve a specific goal in the physical world. Each cognitive tool consists of two major parts: • The camera to be used - front / back, as well as camera parameters - resolution, flashlight etc. • The prompts used for LLM processing. LLM is the bridge between raw pixel data and your interpretation of it, and in the user/system prompt, you can specify what exactly are you interested in for the particular function and how should it be communicated, as well as the LLM model that should be used. Camera input in combination with an LLM processing prompt forms a cognitive function, which can be used to serve various visual tasks. VScan is open-source software. Visit the project's official repository to learn more about its background, motivation, specific usage examples and setup instructions.



